mtmd : rename mtmd_get_audio_bitrate to mtmd_get_audio_sample_rate (#20105)
This commit renames the the function `mtmd_get_audio_bitrate` to `mtmd_get_audio_sample_rate` to better reflect its purpose. The motivation for this is that the function currently returns the audio sample rate, not the bitrate (sample_rate × bit_depth × channels), and that is how it is used in the code as well. This is a breaking change, but I believe mtmd is still in experimental/development phase so it might be alright to simply rename.
This commit is contained in:
@@ -470,12 +470,12 @@ static bool decode_audio_from_buf(const unsigned char * buf_in, size_t len, int
|
|||||||
mtmd_bitmap * mtmd_helper_bitmap_init_from_buf(mtmd_context * ctx, const unsigned char * buf, size_t len) {
|
mtmd_bitmap * mtmd_helper_bitmap_init_from_buf(mtmd_context * ctx, const unsigned char * buf, size_t len) {
|
||||||
if (audio_helpers::is_audio_file((const char *)buf, len)) {
|
if (audio_helpers::is_audio_file((const char *)buf, len)) {
|
||||||
std::vector<float> pcmf32;
|
std::vector<float> pcmf32;
|
||||||
int bitrate = mtmd_get_audio_bitrate(ctx);
|
const int sample_rate = mtmd_get_audio_sample_rate(ctx);
|
||||||
if (bitrate < 0) {
|
if (sample_rate < 0) {
|
||||||
LOG_ERR("This model does not support audio input\n");
|
LOG_ERR("This model does not support audio input\n");
|
||||||
return nullptr;
|
return nullptr;
|
||||||
}
|
}
|
||||||
if (!audio_helpers::decode_audio_from_buf(buf, len, bitrate, pcmf32)) {
|
if (!audio_helpers::decode_audio_from_buf(buf, len, sample_rate, pcmf32)) {
|
||||||
LOG_ERR("Unable to read WAV audio file from buffer\n");
|
LOG_ERR("Unable to read WAV audio file from buffer\n");
|
||||||
return nullptr;
|
return nullptr;
|
||||||
}
|
}
|
||||||
|
|||||||
+1
-1
@@ -912,7 +912,7 @@ bool mtmd_support_audio(mtmd_context * ctx) {
|
|||||||
return ctx->ctx_a != nullptr;
|
return ctx->ctx_a != nullptr;
|
||||||
}
|
}
|
||||||
|
|
||||||
int mtmd_get_audio_bitrate(mtmd_context * ctx) {
|
int mtmd_get_audio_sample_rate(mtmd_context * ctx) {
|
||||||
if (!ctx->ctx_a) {
|
if (!ctx->ctx_a) {
|
||||||
return -1;
|
return -1;
|
||||||
}
|
}
|
||||||
|
|||||||
+2
-2
@@ -125,9 +125,9 @@ MTMD_API bool mtmd_support_vision(mtmd_context * ctx);
|
|||||||
// whether the current model supports audio input
|
// whether the current model supports audio input
|
||||||
MTMD_API bool mtmd_support_audio(mtmd_context * ctx);
|
MTMD_API bool mtmd_support_audio(mtmd_context * ctx);
|
||||||
|
|
||||||
// get audio bitrate in Hz, for example 16000 for Whisper
|
// get audio sample rate in Hz, for example 16000 for Whisper
|
||||||
// return -1 if audio is not supported
|
// return -1 if audio is not supported
|
||||||
MTMD_API int mtmd_get_audio_bitrate(mtmd_context * ctx);
|
MTMD_API int mtmd_get_audio_sample_rate(mtmd_context * ctx);
|
||||||
|
|
||||||
// mtmd_bitmap
|
// mtmd_bitmap
|
||||||
//
|
//
|
||||||
|
|||||||
Reference in New Issue
Block a user